Waxell

skill

deep-research High risk

daymadedaymade/claude-code-skillsupdated

Creates reusable, source-traced research reports and coordinates provider/mode lanes with original exports. Use for 深度研究, 调研报告, literature reviews, market or company research, and ChatGPT/Kimi/UniFuncs research routes. Technology choice uses tech-selection; competitor code uses competitors-analysis.
daymade's own description, from the skill's files.
Stars
1,534
Version
v2
Copies
0

Overview

blockHigh risk

Waxell rates it high risk: 13 findings, highest severity high.

Highest severity
high
Findings
13
What ran
Static analysis + deep scan

A clean result means nothing alarming in what is published, not a guarantee. How the checks work

We don't republish the skill's instructions. Read them on GitHub at the reviewed commit.

Security

Security scan

Checked yesterday

Result

High risk Waxell rates it high risk: 13 findings, highest severity high.

Checked with static analysis + deep scan: servers it launches, packages it installs at runtime, scripts piped to a shell and bundled binaries. The deep scan also read the instructions for prompt injection and data exfiltration. Nothing was run. How the checks work

Findings (13)

high · 5

  • high

    Agent Snooping: Agent Config Directory Access

    references/counter_review_team_guide.md:162 · skillspector:AS1

  • high

    Privilege Escalation: Credential Access

    references/research-asset-contract.md:115 · skillspector:PE3

  • high

    Excessive Agency: External Model or Provider Selection

    references/subagent_prompt.md:96 · skillspector:EA5

  • high

    Excessive Agency: External Model or Provider Selection

    references/subagent_prompt.md:102 · skillspector:EA5

  • high

    System Prompt Leakage: Direct Prompt Extraction

    scripts/dispatch_context.py:274 · skillspector:P6

medium · 7

  • medium

    Without declared permissions the skill's intent is opaque and cannot be validated.

    SKILL.md:1 · skillspector:LP3

  • medium

    Excessive Agency: Autonomous Decision Making

    SKILL.md:561 · skillspector:EA2

  • medium

    Excessive Agency: Autonomous Decision Making

    references/formatting_rules.md:12 · skillspector:EA2

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_dispatch_context.py:21 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_dispatch_context.py:64 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_provider_runs.py:52 · skillspector:AST4

  • medium

    Dangerous Code Execution: subprocess module call

    tests/test_research_assets.py:56 · skillspector:AST4

low · 1

  • low

    Dangerous Code Execution: Dynamic attribute access via getattr()

    scripts/research_assets.py:403 · skillspector:AST7

Versions

Version history

Each distinct content we have seen, newest first, with the verdict it got at the time.

  1. v22026-11-162 added, 6 changed High riskgot riskier
  2. v12026-11-03 No issues

Files

Files

25 files, 319 KB in total. Names only; open them on GitHub.

  • SKILL.md
  • references/completeness_review_checklist.md
  • references/counter_review_team_guide.md
  • references/enterprise_analysis_frameworks.md
  • references/enterprise_quality_checklist.md
  • references/enterprise_research_methodology.md
  • references/formatting_rules.md
  • references/parallel-provider-ops.md
  • references/provider-run-contract.md
  • references/quality_gates.md
  • references/report-file-collection.md
  • references/report_template_v6.md
  • references/research-asset-contract.md
  • references/research_notes_format.md
  • references/research_plan_checklist.md
  • references/research_report_template.md
  • references/source_accessibility_policy.md
  • references/source_quality_rubric.md
  • references/subagent_prompt.md
  • scripts/dispatch_context.py
  • scripts/provider_runs.py
  • scripts/research_assets.py
  • tests/test_dispatch_context.py
  • tests/test_provider_runs.py
  • tests/test_research_assets.py

See and control which skills your people use

Inside your organization, Waxell scans each skill and plugin before anyone installs it, approves what passes and publishes it to a private marketplace, and puts every MCP tool call behind one governed URL.

30 minutes. No commitment.

SOC 2 Type II attested · ISO/IEC 27001:2022 certified · HIPAA with a BAA · aligned to the EU AI Act and NIST AI RMF

More research skills and plugins

See all